ExpVoyager：动态智能体技能合成的直接经验导航
ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis
AI总结：
针对智能体技能合成中经验知识固定化的问题，提出ExpVoyager框架，将技能合成视为动态导航，按需细粒度访问经验，提升下游任务性能并兼容现有技能。
AI中文摘要：
在LLM智能体中，从经验中学习已成为开发持续学习和扩展能力的自我进化智能体的关键范式。在这一范式中，合成智能体技能已成为将积累的经验转化为可复用的程序性知识的有前景的解决方案，作为运行时为智能体提供支持的驾驭系统的重要层。尽管具有潜力，现有方法大多在下游需求已知之前将过去的经验抽象为固定的程序性知识，这有可能丢弃后来变得关键的知识，同时保留与未来任务无关的实例特定细节。在本文中，我们将智能体技能合成重新定义为对过去经验的动态导航问题，其中智能体针对当前任务按需主动探索积累的轨迹，对经验知识进行有针对性和细粒度的访问。为此，我们提出了ExpVoyager，一种新颖的框架，其中技能策展人跨不同视图和分辨率导航原始经验，持续从观察中识别可复用的程序性知识，同时跟踪剩余的知识需求以指导下一步导航。大量实验证明了ExpVoyager的有效性和多功能性，显示了下游任务性能的一致改进、随着经验空间扩展的持续增益，以及在高效经验访问下与现有技能的实际兼容性。
英文摘要：
Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities. Within this paradigm, synthesizing the agent skill has emerged as a promising solution for transforming accumulated experience into reusable procedural knowledge, serving as an important layer for the harness system that supplies agents at runtime. Despite its potential, existing approaches largely abstract past experience into fixed procedural knowledge before downstream demands are known, which risks discarding knowledge that later becomes critical while retaining instance-specific details irrelevant to future tasks. In this paper, we reframe agent skill synthesis as a dynamic navigation problem over past experience, where agents actively explore accumulated trajectories on demand for the current task with targeted and fine-grained access to experience knowledge. To this end, we propose ExpVoyager, a novel framework in which a skill curator navigates raw experience across different views and resolutions, continually identifying reusable procedural knowledge from what it observes while tracking remaining knowledge needs that guide where to navigate next. Extensive experiments demonstrate both the effectiveness and versatility of ExpVoyager, showing consistent improvements in downstream task performance, continual gains as the experience space scales, and practical compatibility with existing skills under efficient experience access.
